Spaces:
Runtime error
Runtime error
File size: 3,463 Bytes
b63ab56 aa4c05b b63ab56 aa4c05b b63ab56 aa4c05b b63ab56 58a98b6 aa4c05b b63ab56 aa4c05b b63ab56 aa4c05b 3238e2c b63ab56 3238e2c b63ab56 3238e2c b63ab56 3238e2c 34812cc b63ab56 34812cc b63ab56 34812cc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 |
# import gradio as gr
# from transformers import AutoTokenizer, AutoModelForCausalLM
# import torch
# model = AutoModelForCausalLM.from_pretrained(
# "Cogwisechat/falcon-7b-finance",
# torch_dtype=torch.bfloat16,
# trust_remote_code=True,
# device_map="auto",
# low_cpu_mem_usage=True,
# )
# tokenizer = AutoTokenizer.from_pretrained("Cogwisechat/falcon-7b-finance")
# def generate_text(input_text):
# global output_text
# input_ids = tokenizer.encode(input_text, return_tensors="pt")
# attention_mask = torch.ones(input_ids.shape)
# output = model.generate(
# input_ids,
# attention_mask=attention_mask,
# max_length=200,
# do_sample=True,
# top_k=10,
# num_return_sequences=1,
# eos_token_id=tokenizer.eos_token_id,
# )
# output_text = tokenizer.decode(output[0], skip_special_tokens=True)
# print(output_text)
# # Remove Prompt Echo from Generated Text
# cleaned_output_text = output_text.replace(input_text, "")
# return cleaned_output_text
# block = gr.Blocks()
# with block:
# gr.Markdown("""<h1><center>CogwiseAI falcon7b</center></h1>
# """)
# # chatbot = gr.Chatbot()
# message = gr.Textbox(placeholder='Enter Your Question Here')
# state = gr.State()
# submit = gr.Button("SEND")
# submit.click(generate_text, inputs=[message, state], outputs=[output_text, state])
# block.launch(debug = True)
# # logo = (
# # "<div >"
# # "<img src='ai-icon.png'alt='image One'>"
# # + "</div>"
# # )
# # text_generation_interface = gr.Interface(
# # fn=generate_text,
# # inputs=[
# # gr.inputs.Textbox(label="Input Text"),
# # ],
# # outputs=gr.inputs.Textbox(label="Generated Text"),
# # title="Falcon-7B Instruct",
# # image=logo
# # ).launch()
from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr
import torch
title = "🦅Falcon 🗨️ChatBot"
description = "Falcon-RW-1B is a 1B parameters causal decoder-only model built by TII and trained on 350B tokens of RefinedWeb."
examples = [["How are you?"]]
tokenizer = AutoTokenizer.from_pretrained("Cogwisechat/falcon-7b-finance")
model = AutoModelForCausalLM.from_pretrained(
"Cogwisechat/falcon-7b-finance",
trust_remote_code=True,
)
def predict(input, history=[]):
# tokenize the new input sentence
new_user_input_ids = tokenizer.encode(
input + tokenizer.eos_token, return_tensors="pt"
)
# append the new user input tokens to the chat history
bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
# generate a response
history = model.generate(
bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
).tolist()
# convert the tokens to text, and then split the responses into lines
response = tokenizer.decode(history[0]).split("<|endoftext|>")
# print('decoded_response-->>'+str(response))
response = [
(response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
] # convert to tuples of list
# print('response-->>'+str(response))
return response, history
gr.Interface(
fn=predict,
title=title,
description=description,
examples=examples,
inputs=["text", "state"],
outputs=["chatbot", "state"],
theme="finlaymacklon/boxy_violet",
).launch() |